batch_read
[SUPPORT] 133bfff6 — run a batch of DOMAIN-AWARE, CONCURRENT read requests in ONE call. Each request names an 'adapter' + 'operation' + 'args'; independent requests (no depends_on) execute concurrently via asyncio.gather — this is pure in-process dispatch, no subagents/worktrees involved. A reque...
This record as markdown: /tools/io-github-ajc3xc-meridian/batch-read.md
What batch_read does on Meridian
AI agents call batch_read to retrieve information from Meridian without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
requests | array | Yes | Non-empty list of typed read requests. |
project_id | string | — | |
max_requests | integer | — | Optional cap on len(requests) for this call (default 100). |
project_name | string | — | Project name — an alternative to project_id; resolved to the id internally. project_id wins if both are given. |
Parameters from the server's own tool schema.
Why batch_read is rated Low
Even though batch_read only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsHigh parameter count (11 properties)
Attacks that exploit this kind of access
The rule that runs batch_read safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Meridian, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For batch_read, this is the rule to start with:
batch_read is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Meridian, apply this rule, and every batch_read call is checked against it from then on.
Questions about batch_read
[SUPPORT] 133bfff6 — run a batch of DOMAIN-AWARE, CONCURRENT read requests in ONE call. Each request names an 'adapter' + 'operation' + 'args'; independent requests (no depends_on) execute concurrently via asyncio.gather — this is pure in-process dispatch, no subagents/worktrees involved. A request with 'depends_on' (a list of other requests' 'request_id's in this SAME batch) waits only for its own declared prerequisites, not the whole batch; if a prerequisite fails, the dependent resolves immediately with error_code='DEPENDENCY_FAILED' and is never executed. Two requests with the identical adapter+operation+normalized-args+depends_on-set COALESCE to one execution — duplicates come back with cache_hit=true and coalesced_with=<the request_id that actually ran>; pass a non-default cache_policy to opt a specific request out of coalescing. Adapters currently registered: 'sprint_board' with operations 'get_sprint_items' (args: status, show_blocked, include_human, version, include_manual_blocker, include_deferred — same meaning as the get_sprint_items tool) and 'get_sprint_item_pointers' (args: sprint_item_id — 404s if that item belongs to a different project); and 'profile' (PROFILE-7) with operations 'get_profile_layer' (args: scope_type, scope_id), 'list_profile_layers' (args: optional scope_type filter), 'get_effective_profile' (args: optional session_id, user_scope_id, workspace_scope_id — returns the merged, generation-keyed effective profile across all 5 layers), and 'get_profile_layer_revisions' (args: scope_id, optional limit). Returns {results: [{request_id, status, adapter, operation, result, error_code, error_message, elapsed_ms, cache_hit, coalesced_with}], elapsed_ms} — results is ALWAYS in input order. error_code is one of VALIDATION_ERROR, ADAPTER_NOT_FOUND, OPERATION_NOT_FOUND, DEPENDENCY_NOT_FOUND, DEPENDENCY_CYCLE, DEPENDENCY_FAILED, NOT_FOUND, TIMEOUT, INTERNAL_ERROR. This tool is READ-ONLY — for mutations use batch_mutate or execute_batch. It is categorised as a Read tool in the Meridian MCP Server, which means it retrieves data without modifying state.
batch_read accepts 4 parameters: requests, project_id, max_requests, project_name. Required: requests. The full parameter table on this page comes from the server's own tool schema.
Register the Meridian MCP server in PolicyLayer and add a rule for batch_read: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Meridian. Nothing to install.
batch_read is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the batch_read rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for batch_read. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
batch_read is provided by the Meridian MCP server (@meridianmcp/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Meridian, and thousands of servers like it.
This server
Across the catalogue